{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:44:47Z","timestamp":1781783087229,"version":"3.54.5"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Xiamen University President\u2019s Fund Cultivation Project","award":["20720210095"],"award-info":[{"award-number":["20720210095"]}]},{"name":"Wang Deyao Project Fund","award":["0660-T040001"],"award-info":[{"award-number":["0660-T040001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82002529"],"award-info":[{"award-number":["82002529"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z202471014"],"award-info":[{"award-number":["3502Z202471014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Despite advanced diagnostics, 3%\u20135% of cases remain classified as cancer of unknown primary (CUP). DNA methylation, an important epigenetic feature, is essential for determining the origin of metastatic tumors. We presented PathMethy, a novel Transformer model integrated with functional categories and crosstalk of pathways, to accurately trace the origin of tumors in CUP samples based on DNA methylation. PathMethy outperformed seven competing methods in F1-score across nine cancer datasets and predicted accurately the molecular subtypes within nine primary tumor types. It not only excelled at tracing the origins of both primary and metastatic tumors but also demonstrated a high degree of agreement with previously diagnosed sites in cases of CUP. PathMethy provided biological insights by highlighting key pathways, functional categories, and their interactions. Using functional categories of pathways, we gained a global understanding of biological processes. For broader access, a user-friendly web server for researchers and clinicians is available at https:\/\/cup.pathmethy.com.<\/jats:p>","DOI":"10.1093\/bib\/bbae497","type":"journal-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T07:17:26Z","timestamp":1728631046000},"source":"Crossref","is-referenced-by-count":5,"title":["PathMethy: an interpretable AI framework for cancer origin tracing based on DNA methylation"],"prefix":"10.1093","volume":"25","author":[{"given":"Jiajing","family":"Xie","sequence":"first","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361005 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4772-2356","authenticated-orcid":false,"given":"Hailong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Bioinformatics , School of Basic Medical Sciences, , No. 1023, South Shatai Road, Baiyun District, Guangzhou, Guangdong, 510515 ,","place":["China"]},{"name":"Southern Medical University , School of Basic Medical Sciences, , No. 1023, South Shatai Road, Baiyun District, Guangzhou, Guangdong, 510515 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijie","family":"Luo","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361005 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2179-173X","authenticated-orcid":false,"given":"Rongshan","family":"Yu","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]},{"name":"School of Informatics, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361005 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengsha","family":"Tong","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]},{"name":"State Key Laboratory of Cellular Stress Biology , School of Life Sciences, Faculty of Medicine and Life Sciences, , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]},{"name":"Xiamen University , School of Life Sciences, Faculty of Medicine and Life Sciences, , No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"2024101107170975700_ref1","doi-asserted-by":"crossref","first-page":"m4050","DOI":"10.1136\/bmj.m4050","article-title":"Cancer of unknown primary","volume":"371","author":"Lee","year":"2020","journal-title":"BMJ"},{"key":"2024101107170975700_ref2","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1016\/j.jare.2014.11.007","article-title":"A mini review on cancer of unknown primary site: a clinical puzzle for the oncologists","volume":"6","author":"Pavlidis","year":"2015","journal-title":"J Adv Res"},{"key":"2024101107170975700_ref3","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1016\/S1470-2045(16)30297-2","article-title":"Epigenetic profiling to classify cancer of unknown primary: a multicentre, retrospective analysis","volume":"17","author":"Moran","year":"2016","journal-title":"Lancet Oncol"},{"key":"2024101107170975700_ref4","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1200\/JCO.2012.43.3755","article-title":"Molecular gene expression profiling to predict the tissue of origin and direct site-specific therapy in patients with carcinoma of unknown primary site: a prospective trial of the Sarah Cannon research institute","volume":"31","author":"Hainsworth","year":"2013","journal-title":"J Clin Oncol"},{"key":"2024101107170975700_ref5","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1200\/EDBK_100014","article-title":"Cancer of unknown primary site: new treatment paradigms in the era of precision medicine","volume":"38","author":"Hainsworth","year":"2018","journal-title":"Am Soc Clin Oncol Educ Book"},{"key":"2024101107170975700_ref6","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1007\/s12094-011-0679-9","article-title":"Update on the diagnosis of cancer of unknown primary (CUP) origin","volume":"13","author":"Ariza","year":"2011","journal-title":"Clin Transl Oncol"},{"key":"2024101107170975700_ref7","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.gde.2017.06.007","article-title":"DNA methylation and the preservation of cell identity","volume":"46","author":"Bogdanovic","year":"2017","journal-title":"Curr Opin Genet Dev"},{"key":"2024101107170975700_ref8","doi-asserted-by":"crossref","first-page":"5686","DOI":"10.1038\/s41467-023-41015-0","article-title":"DNA methylation profiling to determine the primary sites of metastatic cancers using formalin-fixed paraffin-embedded tissues","volume":"14","author":"Zhang","year":"2023","journal-title":"Nat Commun"},{"key":"2024101107170975700_ref9","article-title":"Accurate prediction of pan-cancer types using machine learning with minimal number of DNA methylation sites","volume":"15","author":"Ning","journal-title":"J Mol Cell Biol"},{"key":"2024101107170975700_ref10","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae316","article-title":"Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data","volume":"40","author":"Liu","year":"2024","journal-title":"Bioinformatics"},{"key":"2024101107170975700_ref11","doi-asserted-by":"crossref","first-page":"100797","DOI":"10.1016\/j.crmeth.2024.100797","article-title":"Tracing unknown tumor origins with a biological-pathway-based transformer model","volume":"4","author":"Xie","year":"2024","journal-title":"Cell Rep Methods"},{"key":"2024101107170975700_ref12","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41467-023-35923-4","article-title":"Transformer for one stop interpretable cell type annotation","volume":"14","author":"Chen","year":"2023","journal-title":"Nat Commun"},{"key":"2024101107170975700_ref13","doi-asserted-by":"crossref","first-page":"100619","DOI":"10.1016\/j.xpro.2021.100619","article-title":"Protocol for HSDFinder: identifying, annotating, categorizing, and visualizing duplicated genes in eukaryotic genomes","volume":"2","author":"Zhang","year":"2021","journal-title":"STAR Protoc"},{"key":"2024101107170975700_ref14","doi-asserted-by":"crossref","first-page":"4627","DOI":"10.1038\/s41467-018-06715-y","article-title":"Epigenetic profiling for the molecular classification of metastatic brain tumors","volume":"9","author":"Orozco","year":"2018","journal-title":"Nat Commun"},{"key":"2024101107170975700_ref15","doi-asserted-by":"crossref","first-page":"5068","DOI":"10.1038\/s41467-018-07466-6","article-title":"Comprehensive human cell-type methylation atlas reveals origins of circulating cell-free DNA in health and disease","volume":"9","author":"Moss","year":"2018","journal-title":"Nat Commun"},{"key":"2024101107170975700_ref16","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1002\/path.5845","article-title":"Machine learning models predict the primary sites of head and neck squamous cell carcinoma metastases based on DNA methylation","volume":"256","author":"Leitheiser","year":"2022","journal-title":"J Pathol"},{"key":"2024101107170975700_ref17","doi-asserted-by":"crossref","first-page":"D109","DOI":"10.1093\/nar\/gkr988","article-title":"KEGG for integration and interpretation of large-scale molecular data sets","volume":"40","author":"Kanehisa","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024101107170975700_ref18","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1038\/nprot.2017.144","article-title":"A graphical and computational modeling platform for biological pathways","volume":"13","author":"Livigni","year":"2018","journal-title":"Nat Protoc"},{"key":"2024101107170975700_ref19","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkw849","article-title":"A novel method for crosstalk analysis of biological networks: improving accuracy of pathway annotation","volume":"45","author":"Ogris","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024101107170975700_ref20","article-title":"Machine learning approaches to classify primary and metastatic cancers using tissue of origin-based DNA methylation profiles","volume":"13","author":"Modhukur","journal-title":"Cancers (Basel)"},{"key":"2024101107170975700_ref21","first-page":"zcad017","article-title":"HiTAIC: hierarchical tumor artificial intelligence classifier traces tissue of origin and tumor type in primary and metastasized tumors using DNA methylation, NAR","volume":"5","author":"Zhang","year":"2023","journal-title":"Cancer"},{"key":"2024101107170975700_ref22","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu"},{"key":"2024101107170975700_ref23","doi-asserted-by":"crossref","first-page":"4834","DOI":"10.1038\/s41467-018-07394-5","article-title":"NUAK2 is a critical YAP target in liver cancer","volume":"9","author":"Yuan","year":"2018","journal-title":"Nat Commun"},{"key":"2024101107170975700_ref24","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1016\/j.ccell.2018.03.010","article-title":"Comparative molecular analysis of gastrointestinal adenocarcinomas","volume":"33","author":"Liu","year":"2018","journal-title":"Cancer Cell"},{"key":"2024101107170975700_ref25","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.ccell.2018.03.014","article-title":"A comprehensive pan-cancer molecular study of Gynecologic and breast cancers","volume":"33","author":"Berger","year":"2018","journal-title":"Cancer Cell"},{"key":"2024101107170975700_ref26","doi-asserted-by":"crossref","first-page":"105035","DOI":"10.1016\/j.jbc.2023.105035","article-title":"Mitochondrial cytochrome P450 1B1 is involved in pregnenolone synthesis in human brain cells","volume":"299","author":"Lin","year":"2023","journal-title":"J Biol Chem"},{"key":"2024101107170975700_ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/03602532.2020.1858856","article-title":"Cytochrome P450 expression and regulation in the brain","volume":"53","author":"Kuban","year":"2021","journal-title":"Drug Metab Rev"},{"key":"2024101107170975700_ref28","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani"},{"key":"2024101107170975700_ref29","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Ranftl"},{"key":"2024101107170975700_ref30","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.385","article-title":"Quantifying attention flow in transformers","author":"Abnar","year":"2020"},{"key":"2024101107170975700_ref31","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac285","article-title":"Molecular substructure tree generative model for de novo drug design","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024101107170975700_ref32","doi-asserted-by":"publisher","DOI":"10.3390\/ijms232213919","article-title":"DRPreter: interpretable anticancer drug response prediction using knowledge-guided graph neural networks and transformer","volume":"23","author":"Shin","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2024101107170975700_ref33","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/978-1-4939-8973-7_2","article-title":"Cell-free DNA: an overview of sample types and isolation procedures","volume":"1909","author":"Martignano","year":"2019","journal-title":"Methods Mol Biol"},{"key":"2024101107170975700_ref34","doi-asserted-by":"crossref","first-page":"517","DOI":"10.21037\/tlcr.2016.10.15","article-title":"Liquid biopsy in early stage lung cancer","volume":"5","author":"Perez-Ramirez","year":"2016","journal-title":"Transl Lung Cancer Res"},{"key":"2024101107170975700_ref35","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.csbj.2021.12.001","article-title":"Computational challenges in detection of cancer using cell-free DNA methylation","volume":"20","author":"Sharma","year":"2022","journal-title":"Comput Struct Biotechnol J"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae497\/59716689\/bbae497.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae497\/59716689\/bbae497.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T07:17:54Z","timestamp":1728631074000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae497\/7818162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae497","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,9,23]]},"article-number":"bbae497"}}